feat: add board defaults for model, reasoning effort and preset

README.md

@@ -158,7 +158,7 @@ agent：
 - **任务级 preset（0.3.3）**：新建/编辑表单「执行模式（preset）」下拉——执行会话按该 preset 组合（工具集与人设由此而来，对齐 GUI 新会话的组合方式）；默认预选部署默认 preset，也可选「跟随部署默认」；preset 损坏时执行直接失败并把原因写进执行记录（不产出半组合会话）；随时可改，下轮执行生效
 - **Git Worktree 隔离执行（0.3.0）**：任务级开关（0.5.0 起新建任务的默认值由「看板设置」统一决定，出厂默认原目录执行），每次执行在 `<项目>/.dsh-worktrees/<任务ID>` 独立 worktree 上进行，分支 `task/<标题>+<任务ID>`（首次创建后定死，改名不改）；执行会话归属项目根目录（分组、工具与文件沙箱完整可用——DSH 要求会话 cwd 即工作区根，0.3.2 修正），worktree 路径与边界纪律在开场指令中明确下达；结算自动采集提交列表 / 未提交修改警告 / 改动统计；非 git 项目或 git 不可用时自动降级原目录执行（执行记录注明降级原因，台账与执行主流程永不因 git 失败而失败）；验收时详情页一键 `--no-ff` 合并到主工作区（主区脏或冲突原样报告，不自动解决）、删除 worktree（有未提交修改时拒绝）、可选删分支；支持「↻ 续跑」在现有 worktree/分支上继续执行（保留上次改动与提交）
 - **多仓库镜像隔离（0.6.3）**：工作区内并列多个 git 仓库时（根仓库 + 嵌套独立仓库），worktree 模式自动升级为「任务镜像」——有界扫描发现全部仓库（深度 ≤3、上限 8 个、60s 缓存；submodule 与 linked worktree 形态跳过），每仓库各自建立同名任务分支的 worktree，按相对路径挂进 `<项目>/.dsh-worktrees/<任务ID>/` 形成结构同构镜像；执行引导逐仓库给出镜像路径与分支并声明边界纪律（未镜像仓库禁改）；提交证据、diff 查看（`?repo=` 按仓库）与合并（逐仓库 `--no-ff`，一仓冲突不阻断他仓，按仓库汇总）均分仓库进行；镜像清理聚合全部仓库的未提交检查后「先子后根」删除；任务与执行记录新增 `branches` / `repos` 附加字段，单仓库行为与旧数据零变化；根仓库以 gitlink（embedded repo）形式跟踪子仓的容器工作区同样完全可用——嵌套子镜像在根镜像 status 中的结构性噪音（未跟踪目录 / gitlink 漂移）已在证据采集、合并检查与镜像清理中自动豁免；新建任务表单在多仓库工作区显示「将镜像 N 个仓库」提示，纯容器工作区（根非仓库、只有并列子仓）同样可选 Worktree 隔离
-- **看板设置（0.5.0）**：顶栏「🛠 设置」——选择新建任务默认怎么执行（🌿 Worktree 隔离 / 📁 原目录执行，出厂默认后者）。保存后新建的任务都按它来；之后改设置，已建好的任务不受影响
+- **看板设置**：顶栏「🛠 设置」——统一配置新建任务的默认模型、推理强度、Agent preset、执行隔离与权限。推理强度随模型保存，切换模型时重置为跟随模型默认。任务或模板的显式选择优先；GUI 与 `taskboard_create` 创建时将默认值存入新任务，后续改设置不影响已有任务。未配置看板模型时，GUI 保留原有的上次模型选择记忆；新建表单也可主动选择跟随部署默认。配置随台账持久化并支持 JSON 导入导出。
   > Worktree 隔离是协作约定而非沙箱：执行会话拥有完整工具权限，隔离依赖分支约定，不适用于运行不可信代码的场景。
 - host 侧调度：关掉浏览器照常触发；错过窗口跳过不补跑
 - 乐观并发（ifVersion）+ 完整归因（谁改的、哪个会话执行的）

README_en.md

@@ -156,7 +156,7 @@ Available in any session. Project boundary: only sessions belonging to the task'
 - **Per-task presets (0.3.3)**: an "execution mode (preset)" dropdown in the create/edit form — execution sessions are composed from that preset (tool sets and persona come from it, matching how the GUI composes new sessions); defaults to the deployment default preset, or pick "follow deployment default"; a broken preset fails the execution outright and records why in the execution history (no half-composed sessions); changeable anytime, effective next round
 - **Git worktree isolated execution (0.3.0)**: per-task toggle (since 0.5.0 the default for newly created tasks comes from Board Settings; factory default runs in place). Every execution happens on a dedicated worktree at `<project>/.dsh-worktrees/<taskId>`, branch `task/<title>+<taskId>` (fixed after first creation; renaming doesn't rename branches). The executing session stays rooted at the project directory (grouping, tools, and the file sandbox fully available — DSH requires session cwd === workspace root, fixed in 0.3.2), and the worktree path plus boundary rules are spelled out in the opening instructions. Settlement collects commit lists / uncommitted-changes warnings / change stats automatically. Non-git projects or missing git degrade gracefully to in-place execution (the reason is recorded; the ledger and execution flow never fail because of git). At acceptance: one-click `--no-ff` merge into the main working tree (dirty tree / conflicts reported verbatim, never auto-resolved), worktree deletion (refused with uncommitted changes), optional branch deletion. "↻ Resume" continues on the existing worktree/branch (previous commits and edits kept)
 - **Multi-repo mirror isolation (0.6.3)**: when a workspace holds several parallel git repositories (a root repo plus nested independent ones), worktree mode upgrades into a whole-workspace task mirror — a bounded scan discovers every repo (depth ≤3, capped at 8, 60s cache; submodule / linked-worktree shapes are skipped), each repo gets its own worktree on the same task branch mounted at its relative path under `<project>/.dsh-worktrees/<taskId>/`; the session framing lists every repo's mirror path and branch and marks un-mirrored repos do-not-touch; commit evidence, diff viewing (`?repo=`) and merging (per-repo `--no-ff`, one conflict never blocking the others, per-repo summaries) all work per repo; mirror cleanup aggregates dirty checks across all repo worktrees and removes children before the root; the new `branches` / `repos` record fields are purely additive — single-repo behavior and old data are untouched; container workspaces whose root repo tracks sub-repos as gitlinks (embedded repos) are fully supported too — the structural noise nested child mirrors produce in the root mirror's status (untracked directories / gitlink drift) is exempted automatically from evidence collection, merge clean-checks, and mirror removal; the create-task form shows an "mirrors N repos" note on multi-repo workspaces, and pure-container workspaces (root not a repo, parallel sub-repos only) can pick worktree isolation too
-- **Board settings (0.5.0)**: "🛠 Settings" in the toolbar — choose how new tasks execute by default (🌿 Worktree isolation / 📁 run in place; factory default is the latter). Saving applies to newly created tasks; later changes never affect existing ones
+- **Board settings**: "🛠 Settings" in the toolbar configures the default model, reasoning effort, Agent preset, isolation, and permission for new tasks. Effort is saved with its model and resets to the model default when switching models. Explicit task or template choices win; both the GUI and `taskboard_create` materialize board defaults onto new tasks, so later settings changes never rewrite existing tasks. Without a board model default, the GUI retains its remembered last model; the task form can also explicitly follow deployment defaults. Settings persist with the ledger and support JSON import/export.
   > Worktree isolation is a collaboration convention, not a sandbox: execution sessions hold full tool permissions, isolation rests on the branch convention, and it is not suitable for running untrusted code.
 - Host-side scheduling: fires with the browser closed; missed windows are skipped, never replayed
 - Optimistic concurrency (ifVersion) + full attribution (who changed what, which session executed)